The role, as published
About the company
Our client is a technology company.
The role
Raydar is recruiting for this role on behalf of our client. Plan and carry out machine learning experiments that clarify how different training data shapes model behavior. Convert the findings into practical recommendations and contribute to shared evaluation tooling, collaborating with outside partners and internal colleagues.
What you'll do
- Run controlled fine-tuning and reinforcement learning experiments to measure how training data affects model performance.
- Help build public evaluations and new kinds of training data.
- Share findings publicly through articles, written reports and similar technical content.
- Partner with internal teams to improve data quality based on experimental findings.
- Present results to external partners as clear, well-supported evidence.
What we're looking for
- Strong familiarity with large language model training and evaluation methods.
- Hands-on experience setting up, running and interpreting controlled experiments without close supervision.
- Skill at running quick, small-scale tests and drawing useful conclusions from noisy results.
- Comfort working across several domains, such as finance, software engineering and policy.
- A preference for building and testing over theorizing.
- Prior experience at a leading AI research lab.
- 0 to 4 years of relevant experience.
Benefits
- Health insurance
Location and work model
- San Francisco, California, United States
- On-site
- Full-time